Beruflich Dokumente
Kultur Dokumente
Probability
This chapter introduced us to
the basic ideas behind probability
and the study of randomness.
We learned how to calculate and
interpret the probability of
events in a number of different
situations.
Probability
Probability is a measurement of the likelihood of an
event. It represents the proportion of times wed
expect to see an outcome in a long series of
repetitions.
# success
P(event) =
# possible
Probability Rules
The following facts/formulas are helpful in
calculating and interpreting the probability of an
event:
0 ! P(A) ! 1
P(SampleSpace) = 1
P(AC) = 1 - P(A)
P(A or B) = P(A) + P(B) - P(both)
P(A then B) = P(A) P(B|A)
A and B are independent iff P(B) = P(B|A)
Strategies
When calculating probabilities, it helps to consider
the Sample Space.
List all outcomes if possible.
Draw a tree diagram or Venn diagram
Use the Multiplication Counting Principle
Sometimes it is easier to use common sense rather
than memorizing formulas!
Chapter 7:
Random
Variables
This chapter introduced us to
the concept of a random
variable.
We learned how to describe an
expected value and variability of
both discrete and continuous
random variables.
Random Variable
A Random Variable, X, is a variable whose outcome
is unpredictable in the short-term, but shows a
predictable pattern in the long run.
Discrete vs.
Continuous
Expected Value
The Expected Value, E(X)=, is the long-term
average value of a Random Variable.
X
P(x)
1
0.5
5
0.2
20
0.3
Variance
2
!
The Variance,Var(X)= , is the amount of variability
X
P(x)
1
0.5
5
0.2
20
0.3
! 2 = (1 " 7.5)2 (0.5) + (5 " 7.5)2 (0.2) + (20 " 7.5)2 (0.3)
= 21.125 + 1.25 + 46.875
= 69.25
! = 69.25 = 8.32
a +bX = a + bX
X Y = X Y
a +bX
=b !
2
2
X
X Y
=!
2
X
+!
2
Y
Chapter 8:
Binomial and
Geometric
Distributions
Binomial Setting
Some Random Variables are the result of events
that have only two outcomes (success and failure).
We define a Binomial Setting to have the following
features
Two Outcomes - success/failure
Fixed number of trials - n
Independent trials
Equal P(success) for each trial
Binomial Probabilities
If X is B(n,p), the following formulas can be used to
calculate the probabilities of events in X.
P(X = k) = n Ck ( p) (1 ! p)
= binompdf (n, p, k)
k
n! k
Normal Approximation
If conditions are met, a binomial situation may be
approximated by a normal distribution
If np"10 and n(1-p)"10, then B(n,p) ~ Normal
X = np
! X = np(1 " p)
Geometric Setting
Some Random Variables are the result of events that
have only two outcomes (success and failure), but
have no fixed number of trials. We define a
Geometric Setting to have the following features
Two Outcomes - success/failure
No Fixed number of trials
Independent trials
Equal P(success) for each trial
Geometric Probabilities
If X is Geometric, the following formulas can be
used to calculate the probabilities of events in X.
1
X =
p
1" p
!X =
2
p
P(X = k) = (1 ! p)
= geompdf ( p, k)
P(X > k) = (1 ! p)
k !1
Chapter 9:
Sampling
Distributions
Sampling Distribution
When we take a sample,
we are not guaranteed the
statistic we measure is
equal to the parameter in
question. Further,
repeated sampling may
result in different statistic
values.
Bias and Variability
Sampling Distributions
Proportions
If the population proportion is # and
n#"10, n(1-#)"10 and pop>10n
Then the distribution of p-hat is approximately normal
Sampling Distributions
Means
If the population mean is (and we know ! )
If the population is Normal OR n"30 (CLT)
Then the distribution of x-bar is approximately normal
Sampling Distributions
If conditions are met, we know what the sampling
distribution of a proportion or mean will look like.
Specifically, we know what sample value wed expect to
see and we know how close repeated samples should
come to that expected value.
Since the distributions are normal, we can calculate the
likelihood of observing specific sample values...
This is the basis for the inferential calculations well
study next semester!